Merge branch 'x86/urgent' into x86/pat

Conflicts:
	arch/x86/mm/pageattr.c

Signed-off-by: Ingo Molnar <mingo@elte.hu>

10 files changed, 86 insertions, 28 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 446c658..0bd9c2d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -77,9 +77,6 @@ config FLAT_NODE_MEM_MAP
 	def_bool y
 	depends on !SPARSEMEM
 
-config HAVE_GET_USER_PAGES_FAST
-	bool
-
 #
 # Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's
 # to represent different areas of memory.  This variable allows
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 4af15d0..e023c68 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -473,7 +473,7 @@ find_block:
 				goto find_block;
 			}
 
-		if (bdata->last_end_off &&
+		if (bdata->last_end_off & (PAGE_SIZE - 1) &&
 				PFN_DOWN(bdata->last_end_off) + 1 == sidx)
 			start_off = ALIGN(bdata->last_end_off, align);
 		else
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 757ca98..67a7119 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -565,7 +565,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 		huge_page_order(h));
 	if (page) {
 		if (arch_prepare_hugepage(page)) {
-			__free_pages(page, HUGETLB_PAGE_ORDER);
+			__free_pages(page, huge_page_order(h));
 			return NULL;
 		}
 		prep_new_huge_page(h, page, nid);
@@ -665,6 +665,11 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
 					__GFP_REPEAT|__GFP_NOWARN,
 					huge_page_order(h));
 
+	if (page && arch_prepare_hugepage(page)) {
+		__free_pages(page, huge_page_order(h));
+		return NULL;
+	}
+
 	spin_lock(&hugetlb_lock);
 	if (page) {
 		/*
@@ -1937,6 +1942,18 @@ retry:
 			lock_page(page);
 	}
 
+	/*
+	 * If we are going to COW a private mapping later, we examine the
+	 * pending reservations for this page now. This will ensure that
+	 * any allocations necessary to record that reservation occur outside
+	 * the spinlock.
+	 */
+	if (write_access && !(vma->vm_flags & VM_SHARED))
+		if (vma_needs_reservation(h, vma, address) < 0) {
+			ret = VM_FAULT_OOM;
+			goto backout_unlocked;
+		}
+
 	spin_lock(&mm->page_table_lock);
 	size = i_size_read(mapping->host) >> huge_page_shift(h);
 	if (idx >= size)
@@ -1962,6 +1979,7 @@ out:
 
 backout:
 	spin_unlock(&mm->page_table_lock);
+backout_unlocked:
 	unlock_page(page);
 	put_page(page);
 	goto out;
@@ -1973,6 +1991,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t *ptep;
 	pte_t entry;
 	int ret;
+	struct page *pagecache_page = NULL;
 	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
 	struct hstate *h = hstate_vma(vma);
 
@@ -1989,25 +2008,44 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	entry = huge_ptep_get(ptep);
 	if (huge_pte_none(entry)) {
 		ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
-		mutex_unlock(&hugetlb_instantiation_mutex);
-		return ret;
+		goto out_unlock;
 	}
 
 	ret = 0;
 
+	/*
+	 * If we are going to COW the mapping later, we examine the pending
+	 * reservations for this page now. This will ensure that any
+	 * allocations necessary to record that reservation occur outside the
+	 * spinlock. For private mappings, we also lookup the pagecache
+	 * page now as it is used to determine if a reservation has been
+	 * consumed.
+	 */
+	if (write_access && !pte_write(entry)) {
+		if (vma_needs_reservation(h, vma, address) < 0) {
+			ret = VM_FAULT_OOM;
+			goto out_unlock;
+		}
+
+		if (!(vma->vm_flags & VM_SHARED))
+			pagecache_page = hugetlbfs_pagecache_page(h,
+								vma, address);
+	}
+
 	spin_lock(&mm->page_table_lock);
 	/* Check for a racing update before calling hugetlb_cow */
 	if (likely(pte_same(entry, huge_ptep_get(ptep))))
-		if (write_access && !pte_write(entry)) {
-			struct page *page;
-			page = hugetlbfs_pagecache_page(h, vma, address);
-			ret = hugetlb_cow(mm, vma, address, ptep, entry, page);
-			if (page) {
-				unlock_page(page);
-				put_page(page);
-			}
-		}
+		if (write_access && !pte_write(entry))
+			ret = hugetlb_cow(mm, vma, address, ptep, entry,
+							pagecache_page);
 	spin_unlock(&mm->page_table_lock);
+
+	if (pagecache_page) {
+		unlock_page(pagecache_page);
+		put_page(pagecache_page);
+	}
+
+out_unlock:
 	mutex_unlock(&hugetlb_instantiation_mutex);
 
 	return ret;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7056c3b..0f1f7a7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -796,6 +796,8 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
 
 	if (mem_cgroup_subsys.disabled)
 		return 0;
+	if (!mm)
+		return 0;
 
 	rcu_read_lock();
 	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e550bec..8336905 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -803,7 +803,6 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 int do_migrate_pages(struct mm_struct *mm,
 	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
 {
-	LIST_HEAD(pagelist);
 	int busy = 0;
 	int err = 0;
 	nodemask_t tmp;
diff --git a/mm/mmap.c b/mm/mmap.c
index 971d0ed..339cf5c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2273,14 +2273,14 @@ int install_special_mapping(struct mm_struct *mm,
 
 static DEFINE_MUTEX(mm_all_locks_mutex);
 
-static void vm_lock_anon_vma(struct anon_vma *anon_vma)
+static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
 {
 	if (!test_bit(0, (unsigned long *) &anon_vma->head.next)) {
 		/*
 		 * The LSB of head.next can't change from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		spin_lock(&anon_vma->lock);
+		spin_lock_nest_lock(&anon_vma->lock, &mm->mmap_sem);
 		/*
 		 * We can safely modify head.next after taking the
 		 * anon_vma->lock. If some other vma in this mm shares
@@ -2296,7 +2296,7 @@ static void vm_lock_anon_vma(struct anon_vma *anon_vma)
 	}
 }
 
-static void vm_lock_mapping(struct address_space *mapping)
+static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
 {
 	if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
 		/*
@@ -2310,7 +2310,7 @@ static void vm_lock_mapping(struct address_space *mapping)
 		 */
 		if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
 			BUG();
-		spin_lock(&mapping->i_mmap_lock);
+		spin_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem);
 	}
 }
 
@@ -2358,11 +2358,17 @@ int mm_take_all_locks(struct mm_struct *mm)
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		if (signal_pending(current))
 			goto out_unlock;
-		if (vma->anon_vma)
-			vm_lock_anon_vma(vma->anon_vma);
 		if (vma->vm_file && vma->vm_file->f_mapping)
-			vm_lock_mapping(vma->vm_file->f_mapping);
+			vm_lock_mapping(mm, vma->vm_file->f_mapping);
+	}
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (signal_pending(current))
+			goto out_unlock;
+		if (vma->anon_vma)
+			vm_lock_anon_vma(mm, vma->anon_vma);
 	}
+
 	ret = 0;
 
 out_unlock:
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 8a5467e..64e5b4b 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/notifier.h>
 #include <linux/memcontrol.h>
+#include <linux/security.h>
 
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
@@ -128,7 +129,8 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	 * Superuser processes are usually more important, so we make it
 	 * less likely that we kill those.
 	 */
-	if (__capable(p, CAP_SYS_ADMIN) || __capable(p, CAP_SYS_RESOURCE))
+	if (has_capability(p, CAP_SYS_ADMIN) ||
+	    has_capability(p, CAP_SYS_RESOURCE))
 		points /= 4;
 
 	/*
@@ -137,7 +139,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	 * tend to only have this flag set on applications they think
 	 * of as important.
 	 */
-	if (__capable(p, CAP_SYS_RAWIO))
+	if (has_capability(p, CAP_SYS_RAWIO))
 		points /= 4;
 
 	/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 401d104..af982f7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4437,7 +4437,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 	do {
 		size = bucketsize << log2qty;
 		if (flags & HASH_EARLY)
-			table = alloc_bootmem(size);
+			table = alloc_bootmem_nopanic(size);
 		else if (hashdist)
 			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
 		else {
diff --git a/mm/sparse.c b/mm/sparse.c
index 5d9dbbb..39db301 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -12,7 +12,6 @@
 #include <asm/dma.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
-#include "internal.h"
 
 /*
  * Permanent SPARSEMEM data:
diff --git a/mm/util.c b/mm/util.c
index 9341ca7..cb00b74 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -171,3 +171,18 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	mm->unmap_area = arch_unmap_area;
 }
 #endif
+
+int __attribute__((weak)) get_user_pages_fast(unsigned long start,
+				int nr_pages, int write, struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	down_read(&mm->mmap_sem);
+	ret = get_user_pages(current, mm, start, nr_pages,
+					write, 0, pages, NULL);
+	up_read(&mm->mmap_sem);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(get_user_pages_fast);